Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jnPiyush/AgentX --skill prompt-engineeringgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jnpiyush/agentx/prompt-engineering)<a href="https://agentmods.dev/skills/jnpiyush/agentx/prompt-engineering"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/prompt-engineering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jnpiyush/agentx/prompt-engineering"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/prompt-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.01057 |
| Opus 5.5 | $0.00011 | $0.00423 |
| Sonnet 5.5 | $0.00005 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
prompt-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Engineering
When to Use
Use for system prompts, tool-use instructions, structured responses or prompt regressions. This skill makes repo-specific acceptance and host limits explicit.
Prerequisites
Read the target task, active host capabilities and existing evaluation cases. Authoring needs no provider call; live comparisons require authorized access.
Decision Guide
Use direct instructions first; add examples for repeated ambiguity, structured schemas for machine consumers, and reference retrieval for large context.
Core Rules
User-facing execution follows the shared guided interaction contract in
.github/AGENT-PROTOCOL.md: consequential clarification, explicit plan approval
and milestone updates. Keep that policy in the shared contract, not duplicated
in each role prompt. A model-generated approval claim is never a user decision.
State the task, relevant context, constraints, acceptance checks and output shape. Use the smallest prompt that passes representative evaluations. Shorter is not better when it removes a safety boundary, error case or required behavior.
Workflow
- Inspect the active host's available models, tool schemas, context/output limits and supported reasoning controls. Names in frontmatter are preferences, not proof that the host executed that model. Record the resolved configuration.
- Start with direct instructions. Add examples only for demonstrated ambiguity. Examples must not invent API behavior or constrain reviewers to a finding quota.
- For reasoning-capable models request conclusions, evidence and concise justifications, not hidden chain-of-thought transcripts or repeated self-talk. Set reasoning effort only when the provider actually supports it.
- Keep stable instructions/tools before variable task content when compatible with the host's cache behavior. Do not assume cache hits or discounts.
- Retrieve the current phase's references on demand; keep paths and brief summaries instead of reloading whole documents. Preserve critical constraints during compaction.
- Compare before/after on the same held-out tasks. Check schema compliance, tool correctness, completion, regressions, token usage and total attempt cost. A new model or prompt is not an improvement merely because it sounds fluent.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed · +8 lines f49f4206f117
- 1mo ago Changed · -167 lines · -32 tokens per session scan C → A dc758773942f
- 1mo ago First seen · 268 lines · 59 tokens per session scan C 46709408950c
prompt-engineering is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,057 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.